From: Robert Hancock <hancockr@shaw.ca>
To: linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: sched_yield() makes OpenLDAP slow
Date: Sat, 20 Aug 2005 19:04:32 -0600 [thread overview]
Message-ID: <4307D320.90902@shaw.ca> (raw)
In-Reply-To: <4307788E.1040209@symas.com>
Howard Chu wrote:
> I'll note that we removed a number of the yield calls (that were in
> OpenLDAP 2.2) for the 2.3 release, because I found that they were
> redundant and causing unnecessary delays. My own test system is running
> on a Linux 2.6.12.3 kernel (installed over a SuSE 9.2 x86_64 distro),
> and OpenLDAP 2.3 runs perfectly well here, now that those redundant
> calls have been removed. But I also found that I needed to add a new
> yield(), to work around yet another unexpected issue on this system - we
> have a number of threads waiting on a condition variable, and the thread
> holding the mutex signals the var, unlocks the mutex, and then
> immediately relocks it. The expectation here is that upon unlocking the
> mutex, the calling thread would block while some waiting thread (that
> just got signaled) would get to run. In fact what happened is that the
> calling thread unlocked and relocked the mutex without allowing any of
> the waiting threads to run. In this case the only solution was to insert
> a yield() after the mutex_unlock(). So again, for those of you claiming
> "oh, all you need to do is use a condition variable or any of the other
> POSIX synchronization primitives" - yes, that's a nice theory, but
> reality says otherwise.
I encountered a similar issue with some software that I wrote, and used
a similar workaround, however this was basically because there wasn't
enough time available at the time to redesign things to work properly.
The problem here is essentially caused by the fact that the mutex is
being locked for an excessively large proportion of the time and not
letting other threads in. In the case I am thinking of, posting the
messages to the thread that was hogging the mutex via a signaling queue
would have been a better solution than using yield and having correct
operation depend on undefined parts of thread scheduling behavior..
--
Robert Hancock Saskatoon, SK, Canada
To email, remove "nospam" from hancockr@nospamshaw.ca
Home Page: http://www.roberthancock.com/
next prev parent reply other threads:[~2005-08-21 1:17 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4D8eT-4rg-31@gated-at.bofh.it>
2005-08-20 3:20 ` sched_yield() makes OpenLDAP slow Robert Hancock
2005-08-20 4:18 ` Nick Piggin
2005-08-20 18:38 ` Howard Chu
2005-08-20 20:57 ` Lee Revell
2005-08-20 21:24 ` Howard Chu
2005-08-21 0:36 ` Nick Piggin
2005-08-21 11:33 ` Nikita Danilov
2005-08-22 8:06 ` Howard Chu
2005-08-20 21:50 ` Lee Revell
2005-08-21 1:04 ` Robert Hancock [this message]
2005-08-22 11:44 ` linux-os (Dick Johnson)
2005-08-22 14:26 ` Robert Hancock
2005-08-23 11:17 ` linux-os (Dick Johnson)
2005-08-23 12:07 ` Denis Vlasenko
2005-08-24 3:37 ` Lincoln Dale
2006-01-24 22:59 e100 oops on resume Stefan Seyfried
2006-01-24 23:21 ` Mattia Dongili
2006-01-25 9:02 ` Olaf Kirch
2006-01-25 12:11 ` Olaf Kirch
2006-01-25 13:51 ` sched_yield() makes OpenLDAP slow Howard Chu
2006-01-25 14:38 ` Robert Hancock
2006-01-25 17:49 ` Christopher Friesen
2006-01-26 1:07 ` David Schwartz
2006-01-26 8:30 ` Helge Hafting
2006-01-26 9:01 ` Nick Piggin
2006-01-26 10:50 ` Nikita Danilov
[not found] <5uZqb-4fo-15@gated-at.bofh.it>
2006-01-14 22:47 ` Robert Hancock
-- strict thread matches above, loose matches on Subject: below --
2006-01-14 19:29 Howard Chu
[not found] <43057641.70700@symas.com.suse.lists.linux.kernel>
[not found] ` <17157.45712.877795.437505@gargle.gargle.HOWL.suse.lists.linux.kernel>
[not found] ` <430666DB.70802@symas.com.suse.lists.linux.kernel>
2005-08-20 13:48 ` Andi Kleen
2005-08-21 19:47 ` Florian Weimer
2005-08-22 5:09 ` Howard Chu
2005-08-22 13:06 ` Andi Kleen
2005-08-22 18:47 ` Howard Chu
2005-08-22 13:20 ` Florian Weimer
2005-08-22 23:19 ` Howard Chu
2005-08-19 6:03 Howard Chu
2005-08-19 6:34 ` Nick Piggin
2005-08-19 6:59 ` Chris Wedgwood
2005-08-19 22:45 ` Howard Chu
2005-08-19 10:21 ` Nikita Danilov
2005-08-19 23:10 ` Howard Chu
2005-08-20 13:23 ` Nikita Danilov
2005-08-20 19:49 ` Howard Chu
2005-08-20 22:08 ` Nikita Danilov
[not found] <4303DB48.8010902@develer.com.suse.lists.linux.kernel>
[not found] ` <20050818010703.GA13127@nineveh.rivenstone.net.suse.lists.linux.kernel>
[not found] ` <4303F967.6000404@yahoo.com.au.suse.lists.linux.kernel>
[not found] ` <43054D9A.7090509@develer.com.suse.lists.linux.kernel>
2005-08-19 3:19 ` Andi Kleen
2005-08-19 3:30 ` Bernardo Innocenti
2005-08-18 0:50 Bernardo Innocenti
2005-08-18 0:47 ` Con Kolivas
2005-08-18 10:48 ` Maciej Soltysiak
2005-08-18 1:07 ` Joseph Fannin
2005-08-18 2:25 ` Bernardo Innocenti
2005-08-18 2:58 ` Nick Piggin
2005-08-19 3:10 ` Bernardo Innocenti
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4307D320.90902@shaw.ca \
--to=hancockr@shaw.ca \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox